© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23230
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and subsequent expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    èĢĮ论
    -0.07
    åĴĮåķĨä¸ļ
    -0.07
    czyn
    -0.07
    âĢ¦âĢ¦ãĢĤ
    -0.07
    Ĩµ
    -0.07
    ombat
    -0.07
    Ĥ¬
    -0.07
    ä¸įæĶ¹
    -0.07
    ibro
    -0.07
    elman
    -0.07
    POSITIVE LOGITS
    ahme
    0.07
    äºİä¸Ģ
    0.06
    KER
    0.06
    éĿĪéŃĤ
    0.06
    neu
    0.06
    ids
    0.06
    alh
    0.06
    çĿĢåij¢
    0.06
    endenza
    0.06
    ãģ©ãĤĬ
    0.06
    Activations Density 0.007%

    No Known Activations